Gradients and frequency profiles of quantum re-uploading models

Abstract

Quantum re-uploading models have been extensively investigated as a form of machine learning within the context of variational quantum algorithms. Their trainability and expressivity are not yet fully understood and are critical to their performance. In this work, we address trainability through the lens of the magnitude of the gradients of the cost function. We prove bounds for the differences between gradients of the better-studied data-less parameterized quantum circuits and re-uploading models. We coin the concept of {\sl absorption witness} to quantify such difference. For the expressivity, we prove that quantum re-uploading models output functions with vanishing high-frequency components and upper-bounded derivatives with respect to data. As a consequence, such functions present limited sensitivity to fine details, which protects against overfitting. We performed numerical experiments extending the theoretical results to more relaxed and realistic conditions. Overall, future designs of quantum re-uploading models will benefit from the strengthened knowledge delivered by the uncovering of absorption witnesses and vanishing high frequencies.

14 pages + 2 of references + 8 of appendix. 7+1 figures. Updated version after peer-review and acceptance in Quantum

References in corpus (38)

• Quantum Computing in the NISQ era and beyond
• A variational eigenvalue solver on a quantum processor
• Elementary gates for quantum computation
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Chemistry in the Age of Quantum Computing
• Characterizing Quantum Supremacy in Near-Term Devices
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient variational quantum simulator incorporating active error minimisation
• Data re-uploading for a universal quantum classifier
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Variational ansatz-based quantum simulation of imaginary time evolution
• Quantum generative adversarial networks
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Theory of variational quantum simulation
• Training variational quantum algorithms is NP-hard
• Variational Fast Forwarding for Quantum Simulation Beyond the Coherence Time
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Quantum machine learning beyond kernel methods
• Theory of overparametrization in quantum neural networks
• Variational Quantum Boltzmann Machines
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• One qubit as a Universal Approximant
• Generalization despite overfitting in quantum machine learning models
• Determining the proton content with a quantum computer
• Classical surrogates for quantum learning models
• Low depth mechanisms for quantum optimization
• Exponential data encoding for quantum supervised learning
• Analyzing variational quantum landscapes with information content

Cited by in corpus (5)

• Neural quantum kernels: training quantum kernels with quantum neural networks
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Fourier Analysis of Variational Quantum Circuits for Supervised Learning
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits